2011 | OriginalPaper | Buchkapitel
Study on Thermal Conductivities Prediction for Apple Fruit Juice by Using Neural Network
verfasst von : Min Zhang, Zhenhua Che, Jiahua Lu, Huizhong Zhao, Jianhua Chen, Zhiyou Zhong, Le Yang
Erschienen in: Computer and Computing Technologies in Agriculture IV
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Based on experimentally measured values by thermal probe method, the prediction model of thermal conductivities of apple fruit juice as a function of concentration and temperature was studied by neural network method. The optimal neural network was made of two hidden layers and every hidden layer had six neurons. The prediction result shows that the optimal model could predict thermal conductivity with a mean relative error of 0.11%, a mean absolute error of 0.00054W/mK, a mean standard error of 0.00039 W/mK, the linear relationship of 0.9993. The calculated precision was higher for BP neural network model than that for dual regression model. The presented results were proved that this model can be used with satisfactory accuracy for the prediction of thermal conductivity of apple fruit juice.